Agentic Context Engine is an open-source engine that gives AI agents a persistent learning loop, helping them remember successful strategies and learn from failures across sessions. It is used to improve production agents, and also powers Kayba’s hosted service. Catalogue add-ons support workflows for operating and configuring the engine.
Borrowing it
Nothing to install: this file belongs to kayba-ai/agentic-context-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kayba-ai/agentic-context-engine/main/.claude/skills/kayba-pipeline/stage-7-fixer/SKILL.mdgit clone --depth 1 https://github.com/kayba-ai/agentic-context-engineWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kayba-ai/agentic-context-engine/stage-7-fixer)<a href="https://agentmods.dev/skills/kayba-ai/agentic-context-engine/stage-7-fixer"><img src="https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/stage-7-fixer.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.01765 |
| Opus 5 | $0.00030 | $0.00882 |
| Sonnet 5 | $0.00012 | $0.00353 |
| Haiku 4.5 | $0.00006 | $0.00177 |
Grade A, and why
kayba-stage-7-fixer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage 7: Fix Implementation
Implement every non-discarded fix from the approved action plan.
Inputs
eval/action_plan.md-- the approved action plan from Stage 5 (possibly modified during HITL in Stage 6)eval/stage6_decision.md-- if it exists, the HITL decision record from Stage 6 (contains user modifications)eval/baseline_metrics.json-- the pre-fix baseline metrics from Stage 3 (for reference in changes log)
Read the action plan and stage6 decision (if present) before starting.
Pre-flight: Git Safety Checkpoint
Before making ANY changes to source files:
- Run
git statusto confirm the working tree state - Create a safety commit or stash:
If there are no uncommitted changes to stash, create a lightweight tag instead:git stash push -m "pre-pipeline-fixes-$(date +%Y%m%d-%H%M%S)"git tag pre-pipeline-fixes-$(date +%Y%m%d-%H%M%S) - Record the stash ref or tag name in
eval/changes_log.mdunder a "Rollback" section so the user can restore if needed
This ensures every fix is reversible with a single git stash pop or git checkout.
Pre-flight: HITL Modification Check
If eval/stage6_decision.md exists:
- Read it and identify any items the user modified, added, or re-prioritized during Stage 6
- Build a set of
HITL_MODIFIED_IDS-- the insight/skill IDs that the user changed - When logging each fix later, tag modified items with
[HITL-MODIFIED]in the changes log so reviewers know which fixes reflect user judgment vs. the original pipeline output
If the file does not exist, assume no HITL modifications were made.
Pre-flight: Conflict Scan
Before implementing any fixes, scan the action plan for potential conflicts:
- Build a map of
file_path -> [fix IDs that touch it] - If two or more fixes modify the same file, flag them as co-located
- If two or more fixes modify the same section (within ~20 lines of each other), flag them as overlapping
- For overlapping fixes: plan to apply them sequentially in priority order, re-reading the file between each edit to ensure the second fix still makes sense on top of the first
- Log any detected conflicts at the top of
eval/changes_log.mdunder a "Conflict Notes" section
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 192 lines · 61 tokens per session scan A 08b8439bd785
kayba-stage-7-fixer is a skill published in the GitHub repository kayba-ai/agentic-context-engine (2,565 stars, last pushed 10d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,765 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
titen-memory
Use the Titen MCP server to recall bounded evidence-grounded context, record verified durable signals, submit feedback, and coordinate checkpoints, leases, or handoffs. Use when work may benefit from prior project memory or when a verified outcome should be preserved for another agent; do not use it to capture raw…
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
goai
GoAI is a Go SDK for AI applications. One unified API across 25+ LLM providers. Inspired by the Vercel AI SDK, adapted to Go idioms (generics, interfaces, channels).
mnemo-cortex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.